Skip to main content

The Generalization Performance of Learning Machine with NA Dependent Sequence

  • Conference paper
Rough Sets and Knowledge Technology (RSKT 2006)

Part of the book series: Lecture Notes in Computer Science ((LNAI,volume 4062))

Included in the following conference series:

  • 1064 Accesses

Abstract

The generalization performance is the main purpose of machine learning theoretical research. This note mainly focuses on a theoretical analysis of learning machine with negatively associated dependent input sequence. The explicit bound on the rate of uniform convergence of the empirical errors to their expected error based on negatively associated dependent input sequence is obtained by the inequality of Joag-dev and Proschan. The uniform convergence approach is used to estimate the convergence rate of the sample error of learning machine that minimize empirical risk with negatively associated dependent input sequence. In the end, we compare these bounds with previous results.

Supported in part by NSFC under grant 60403011.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Similar content being viewed by others

References

  1. Bousquet, O., Elisseeff, A.: Stability and generalization. Journal of Machine Learning Research 2, 499–526 (2002)

    Article  MATH  MathSciNet  Google Scholar 

  2. Cucker, F., Smale, S.: On the mathematical foundations of learning. Bulletin of the American Mathematical Society 39, 1–49 (2002)

    Article  MATH  MathSciNet  Google Scholar 

  3. Forster, J., Warmuth, M.: Relative expected instantaneous loss bounds. Journal of Computer and System Science 64, 76–102 (2002)

    Article  MATH  MathSciNet  Google Scholar 

  4. Joag-dev, K., Proschan, F.: Negative associated of random variables with applications. Annals of Statistics 11, 286–295 (1983)

    Article  MathSciNet  Google Scholar 

  5. Karandikar, R.L., Vidyasagar, M.: Rates of uniform convergence of empirical means with mixing processes. Statist. Probab. Lett. 58, 297–307 (2002)

    Article  MATH  MathSciNet  Google Scholar 

  6. Nobel, A., Dembo, A.: A note on uniform laws of averages for dependent processes. Statist. Probab. Lett. 17, 169–172 (1993)

    Article  MATH  MathSciNet  Google Scholar 

  7. Vapnik, V.: Statistical Learning Theory. Wiley, New York (1998)

    MATH  Google Scholar 

  8. Vidyasagar, M.: Learning and Generalization with Applications to Neural Networks. Springer, London (2003)

    Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Editor information

Editors and Affiliations

Rights and permissions

Reprints and permissions

Copyright information

© 2006 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Zou, B., Li, L., Xu, J. (2006). The Generalization Performance of Learning Machine with NA Dependent Sequence. In: Wang, GY., Peters, J.F., Skowron, A., Yao, Y. (eds) Rough Sets and Knowledge Technology. RSKT 2006. Lecture Notes in Computer Science(), vol 4062. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11795131_82

Download citation

  • DOI: https://doi.org/10.1007/11795131_82

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-36297-5

  • Online ISBN: 978-3-540-36299-9

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics